@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 649550f27e
Fork 0

A high-throughput and memory-efficient inference and serving engine for LLMs

Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git

Synced Nov 16, 00:45 UTC

[Build] update requirements of no-device for plugin usage (#12630)

Signed-off-by: Sophie du Couédic <sop@zurich.ibm.com>

Sophie du Couédic committed Feb 4, 2025 at 14:19 UTC 649550f27e4ad35e7e3352800438991fdaf150a4
1 file changed +1 -1
setup.py
+1 -1
@@ -556,7 +556,7 @@ def get_requirements() -> List[str]:
556 return resolved_requirements
557
558 if _no_device():
559 - requirements = _read_requirements("requirements-cpu.txt")
559 + requirements = _read_requirements("requirements-common.txt")
560 elif _is_cuda():
561 requirements = _read_requirements("requirements-cuda.txt")
562 cuda_major, cuda_minor = torch.version.cuda.split(".")